INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

azzi

-0.16

utz

-0.15

 terk

-0.15

ÐŀÐĴ

-0.14

 ÑģÐ¾Ñģ

-0.14

olas

-0.14

itar

-0.14

erable

-0.13

layÄ±cÄ±

-0.13

gradable

-0.13

POSITIVE LOGITS

 pole

0.19

 Pole

0.17

ooth

0.16

'gc

0.15

#-

0.15

lod

0.15

 deliveries

0.15

(-

0.15

lod

0.14

 lodge

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.